App Bench
App Bench
Fail · 11
Booking pagePractitioner email could not be checkedCourse sitePurchase and new lessons unverifiedEmail digestDaily email not sent from the previewEvent RSVPConfirmation email could not be checkedLead quizQuote email could not be checkedPaid AI toolSubscription could not be checkedPaid membershipCard payment could not be checkedReview toolManager feedback could not be checkedShopify storeShopify order could not be completedTeam dashboardClosing a ticket was not checkedTemplate shopNo sale possible without a file upload
Pass · 9
AI chatScrappy bike shop with a chat helperClient portalAn editorial studio portalFile converterStatements become a CSVForumA heritage forum for watch restorersListings siteA coffee-magazine roaster directoryReturns trackerA big-screen returns logSite with loginPlayful podcaster site with gated readingTeam CRMA light, shared sales pipelineTeam whiteboardA live weekly board for a small team

persona.md

The customer agent reads persona.md with the spec, and writes each prompt in one style. It sends one prompt at a time. The agent never sees it.

  • Tweak: short commands
  • Describe: a sentence or two
  • Specify: long, exact instructions
  • Brief: one long brief, then small fixes

How the customer acts

  1. Talks like the owner: never mentions the test
  2. Adds detail: when a fix doesn't work
  3. Says what's still wrong: quotes what the agent claimed
  4. Keeps going: until every check passes, or 40 prompts